@article{reinforcementlearningwithoutgroundtruths,
  title = {Reinforcement Learning without Ground-Truth Solutions can Improve LLMs},
  author = {Yingyu Lin and Qiyue Gao and Nikki Lijing Kuang and Xunpeng Huang and Kun Zhou and Tongtong Liang and Zhewei Yao and Yi-An Ma and Yuxiong He},
  year = {2026},
  eprint = {2606.27369},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.27369},
}